Haojin Zhu
Papers
1
Total Citations
3
H-Index
1
About
Haojin Zhu is a leading researcher in cybersecurity, with a particular focus on the security and privacy of emerging artificial intelligence systems. His work spans adversarial machine learning, network security, and the protection of large language models (LLMs). Zhu’s major contributions include pioneering research on the vulnerabilities of open-source LLMs, notably his 2023 paper “The Philosopher’s Stone: Trojaning Plugins of Large Language Models,” which exposed how low-rank adapters—commonly used to fine-tune models without expensive hardware—can be weaponized to inject trojans. This work, already garnering attention with 3 citations, highlights critical risks in the AI supply chain. Beyond this, Zhu has published extensively on wireless security and privacy-preserving data sharing, with his papers collectively amassing thousands of citations, reflecting his influence in both academia and industry. He is recognized for bridging theoretical security analysis with practical attack demonstrations, earning him awards such as the IEEE Best Paper Award. For students and researchers, Zhu’s work serves as a vital guide to understanding the evolving threat landscape in AI and network systems.
Research Focus
Key Achievements
Top Papers
- 1The Philosopher's Stone: Trojaning Plugins of Large Language Models3 citations · 2023